Unverified50% confidenceFactExact time
GPQA于2023年由纽约大学团队提出，题目由领域专家设计，普通网络搜索无法直接查到答案
1
Sources
50%
Confidence
Long-term
Relevance
7/21/2026
First Seen
Sources
Related Claims
UnverifiedGPQA 由纽约大学研究人员于 2023 年设计，包含 1198 道经领域专家验证的题目82% similarUnverifiedGenerative Engine Optimization (GEO) was formally proposed around 2023 by researchers from Princeton University and other institutions.63% similarUnverifiedGPTBot是OpenAI于2023年8月公开的爬虫标识符62% similarUnverified可溯源生成（attributable generation）是 NLP 领域的研究方向，最早由 Google Research 等团队在 2022-2023 年间系统化提出60% similarUnverifiedMTP (Multi-Token Prediction) technology was systematically proposed by Meta in 2024 research and has been adopted by mainstream open-source models such as Qwen and DeepSeek.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/579929API
curl https://kongchang.com/api/v1/knowledge/claims/579929MCP
get_claim(id=579929)